I obtained my Ph.D. in Computer Science and Engineering from the University of Michigan, Ann Arbor. I am interested in machine learning in general, with a recent focus on large scale machine learning algorithms and systems. My Ph.D. dissertation is about using sequential decision making techniques (e.g., multi-armed bandit) to accelerate large scale machine learning (e.g., large language model training). I am very fortunate to be advised by Professor Barzan Mozafari.

I am currently working at Meta to build scalable machine learning models and systems to solve real-world challenges. During my Ph.D. study, I also spent several summers as an intern at Microsoft and Meta.

Publications

• [ OSDI'23 ] AdaEmbed: Adaptive Embedding for Large-Scale Recommendation Models
  Fan Lai, Wei Zhang, Rui Liu, William Tsai, Xiaohan Wei, Yuxi Hu, Sabin Devkota, Jianyu Huang, Jongsoo Park, Xing Liu, Zeliang Chen, Ellie Wen, Paul Rivera, Jie You, Jason Chen, Mosharaf Chowdhury
  Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation, 2023.
  [PDF] 

• [ ICLR'23 ] Coverage-centric Coreset Selection for High Pruning Rates
  Haizhong Zheng, Rui Liu, Fan Lai, Atul Prakash
  Proceedings of the 11th International Conference on Learning Representations, 2023.
  [PDF] 

• [ ICML'22 ] Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers
  Rui Liu, Young Jin Kim, Alexandre Muzio, Hany Hassan Awadalla
  Proceedings of the 39th International Conference on Machine Learning, 2022.
  [PDF]

• [ ICML'22 ] Communication-efficient Distributed Learning for Large Batch Optimization
  Rui Liu, Barzan Mozafari
  Proceedings of the 39th International Conference on Machine Learning, 2022.
  [PDF]

• [ AAAI'22 ] Transformer with Memory Replay
  Rui Liu, Barzan Mozafari
  Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022.
  [PDF]

• [ NeurIPS'20 ] Adam with Bandit Sampling for Deep Learning
  Rui Liu, Tianyi Wu, Barzan Mozafari
  Proceedings of the 34th Conference on Neural Information Processing Systems, 2020.
  [PDF]

• [ AAAI'19 ] A Bandit Approach to Maximum Inner Product Search
  Rui Liu, Tianyi Wu, Barzan Mozafari
  Proceedings of the 33th AAAI Conference on Artificial Intelligence, 2019.
  [PDF] 

• [ ECML/PKDD'19 ] RANKBOOST+: an improvement to RANKBOOST
  Harold Connamacher, Nikil Pancha, Rui Liu, Soumya Ray
  Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019.
  [PDF] 

• [ ICDM'17 ] An Analysis of Boosted Linear Classifiers on Noisy Data with Applications to Multiple-Instance Learning
  Rui Liu, Soumya Ray
  Proceedings of the IEEE International Conference on Data Mining, 2017.
  [PDF] 

• [ ICDM'15 ] Robust Multi-Network Clustering via Joint Cross-Domain Cluster Alignment
  Rui Liu, Wei Cheng, Hanghang Tong, Wei Wang, Xiang Zhang
  Proceedings of the IEEE International Conference on Data Mining, 2015.
  [PDF] 

Services